© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1656
    Prev
    Next
    INDEX
    Explanations

    word endings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bove
    -0.29
    ustralia
    -0.28
    âĸį
    -0.25
    çĭ¬ä¸Ģ
    -0.23
    ä»Ĭ天å°ıç¼ĸ
    -0.23
    pollo
    -0.23
     prostitu
    -0.23
     CircularProgress
    -0.23
    Ç
    -0.22
    rchive
    -0.22
    POSITIVE LOGITS
    åĦ¿
    0.31
    ä¹ĭä½ľ
    0.26
    èĪ¬çļĦ
    0.25
    ingly
    0.23
    edly
    0.23
    å¼ıçļĦ
    0.22
    èĪ¬
    0.20
    å¼ı
    0.20
    äºĨä¸Ģä¸ĭ
    0.20
    åįģ足
    0.20
    Activations Density 8.858%

    No Known Activations